[PATCH 4/7] hvc_console: Fix race between hvc_close and hvc_remove

[Benjamin Herrenschmidt]

On Fri, 2010-03-19 at 08:18 -0700, Greg Kroah-Hartman wrote:
> From: Amit Shah <amit.shah at redhat.com>
> 
> Alan pointed out a race in the code where hvc_remove is invoked. The
> recent virtio_console work is the first user of hvc_remove().

This causes hangs during boot on pseries machines. Haven't had a chance
to track that down yet, but please revert
e74d098c66543d0731de62eb747ccd5b636a6f4c for now.

Cheers,
Ben.


> Alan describes it thus:
> 
> The hvc_console assumes that a close and remove call can't occur at the
> same time.
> 
> In addition tty_hangup(tty) is problematic as tty_hangup is asynchronous
> itself....
> 
> So this can happen
> 
>         hvc_close                               hvc_remove
>         hung up ? - no
>                                                 lock
>                                                 tty = hp->tty
>                                                 unlock
>         lock
>         hp->tty = NULL
>         unlock
>         notify del
>         kref_put the hvc struct
>         close completes
>         tty is destroyed
>                                                 tty_hangup dead tty
>                                                 tty->ops will be NULL
>                                                 NULL->...
> 
> This patch adds some tty krefs and also converts to using tty_vhangup().
> 
> Reported-by: Alan Cox <alan at lxorguk.ukuu.org.uk>
> Signed-off-by: Amit Shah <amit.shah at redhat.com>
> CC: Alan Cox <alan at lxorguk.ukuu.org.uk>
> CC: linuxppc-dev at ozlabs.org
> CC: Rusty Russell <rusty at rustcorp.com.au>
> Signed-off-by: Greg Kroah-Hartman <gregkh at suse.de>
> ---
>  drivers/char/hvc_console.c |   31 +++++++++++++++++++++----------
>  1 files changed, 21 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/char/hvc_console.c b/drivers/char/hvc_console.c
> index 465185f..ba55bba 100644
> --- a/drivers/char/hvc_console.c
> +++ b/drivers/char/hvc_console.c
> @@ -312,6 +312,7 @@ static int hvc_open(struct tty_struct *tty, struct file * filp)
>  	spin_lock_irqsave(&hp->lock, flags);
>  	/* Check and then increment for fast path open. */
>  	if (hp->count++ > 0) {
> +		tty_kref_get(tty);
>  		spin_unlock_irqrestore(&hp->lock, flags);
>  		hvc_kick();
>  		return 0;
> @@ -319,7 +320,7 @@ static int hvc_open(struct tty_struct *tty, struct file * filp)
>  
>  	tty->driver_data = hp;
>  
> -	hp->tty = tty;
> +	hp->tty = tty_kref_get(tty);
>  
>  	spin_unlock_irqrestore(&hp->lock, flags);
>  
> @@ -336,6 +337,7 @@ static int hvc_open(struct tty_struct *tty, struct file * filp)
>  		spin_lock_irqsave(&hp->lock, flags);
>  		hp->tty = NULL;
>  		spin_unlock_irqrestore(&hp->lock, flags);
> +		tty_kref_put(tty);
>  		tty->driver_data = NULL;
>  		kref_put(&hp->kref, destroy_hvc_struct);
>  		printk(KERN_ERR "hvc_open: request_irq failed with rc %d.\n", rc);
> @@ -363,13 +365,18 @@ static void hvc_close(struct tty_struct *tty, struct file * filp)
>  		return;
>  
>  	hp = tty->driver_data;
> +
>  	spin_lock_irqsave(&hp->lock, flags);
> +	tty_kref_get(tty);
>  
>  	if (--hp->count == 0) {
>  		/* We are done with the tty pointer now. */
>  		hp->tty = NULL;
>  		spin_unlock_irqrestore(&hp->lock, flags);
>  
> +		/* Put the ref obtained in hvc_open() */
> +		tty_kref_put(tty);
> +
>  		if (hp->ops->notifier_del)
>  			hp->ops->notifier_del(hp, hp->data);
>  
> @@ -389,6 +396,7 @@ static void hvc_close(struct tty_struct *tty, struct file * filp)
>  		spin_unlock_irqrestore(&hp->lock, flags);
>  	}
>  
> +	tty_kref_put(tty);
>  	kref_put(&hp->kref, destroy_hvc_struct);
>  }
>  
> @@ -424,10 +432,11 @@ static void hvc_hangup(struct tty_struct *tty)
>  	spin_unlock_irqrestore(&hp->lock, flags);
>  
>  	if (hp->ops->notifier_hangup)
> -			hp->ops->notifier_hangup(hp, hp->data);
> +		hp->ops->notifier_hangup(hp, hp->data);
>  
>  	while(temp_open_count) {
>  		--temp_open_count;
> +		tty_kref_put(tty);
>  		kref_put(&hp->kref, destroy_hvc_struct);
>  	}
>  }
> @@ -592,7 +601,7 @@ int hvc_poll(struct hvc_struct *hp)
>  	}
>  
>  	/* No tty attached, just skip */
> -	tty = hp->tty;
> +	tty = tty_kref_get(hp->tty);
>  	if (tty == NULL)
>  		goto bail;
>  
> @@ -672,6 +681,8 @@ int hvc_poll(struct hvc_struct *hp)
>  
>  		tty_flip_buffer_push(tty);
>  	}
> +	if (tty)
> +		tty_kref_put(tty);
>  
>  	return poll_mask;
>  }
> @@ -807,7 +818,7 @@ int hvc_remove(struct hvc_struct *hp)
>  	struct tty_struct *tty;
>  
>  	spin_lock_irqsave(&hp->lock, flags);
> -	tty = hp->tty;
> +	tty = tty_kref_get(hp->tty);
>  
>  	if (hp->index < MAX_NR_HVC_CONSOLES)
>  		vtermnos[hp->index] = -1;
> @@ -819,18 +830,18 @@ int hvc_remove(struct hvc_struct *hp)
>  	/*
>  	 * We 'put' the instance that was grabbed when the kref instance
>  	 * was initialized using kref_init().  Let the last holder of this
> -	 * kref cause it to be removed, which will probably be the tty_hangup
> +	 * kref cause it to be removed, which will probably be the tty_vhangup
>  	 * below.
>  	 */
>  	kref_put(&hp->kref, destroy_hvc_struct);
>  
>  	/*
> -	 * This function call will auto chain call hvc_hangup.  The tty should
> -	 * always be valid at this time unless a simultaneous tty close already
> -	 * cleaned up the hvc_struct.
> +	 * This function call will auto chain call hvc_hangup.
>  	 */
> -	if (tty)
> -		tty_hangup(tty);
> +	if (tty) {
> +		tty_vhangup(tty);
> +		tty_kref_put(tty);
> +	}
>  	return 0;
>  }
>  EXPORT_SYMBOL_GPL(hvc_remove);